Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GLM-5.2 is the new leading open weights model on Artificial Analysis

artificialanalysis.ai

Post reply on HN
Print view View original

41–50 of 476 posts

Re: GLM-5.2 is the new leading open weights model on Artificial Analysis

#41

Post by andai »

Hamuko wrote: post #9
unrvl22 wrote: post #4

Why aren't more people talking about this? It's literally Opus 4.7 quality stupid prices. I know providers who are offering this at unlimited tokens for $50 a month. Some are even offering API rates at 3x lower than the official ZAI api rates which are already like 10x cheaper than Opus. (Crof and Umans btw) This is a huge blow to Anthropic/OpenAI/Google and a massive win for the rest of the world. The official API p…

I’m not that interested in models that I can’t run on my desktop for ~0€, which is my AI budget.

Electricity cost seems to be about $30/month for a 32B model on a GPU. It's probably better on Apple hardware.

https://github.com/QuantiusBenignus/Zshelf/discussions/2

Not accounting for hardware, of course :)

Re: GLM-5.2 is the new leading open weights model on Artificial Analysis

#45

Post by fragmede »

elwebmaster wrote: post #39
igravious wrote: post #20

Earlier quoted context omitted.

After having got a taste of Fable 5 for me Opus 4.8 doesn't cut it any more -- and I don't know how to put this, I don't know if it's just me, but it's rhetorical flourishes are starting to really grate on me, never mind that it is at times deliberately weasel-wordy and economical with the truth until pressed. Opus 4.8 is definitely a stronger coding agent than DeepSeek 4.0 or Kimi 2.7 succeeding where they flounder…

You are not alone. How about GPT 5.5? Does it come close to Fable 5?

5.5 is pretty good. It's no Fable though. It is definitely better than opus tho.

Re: GLM-5.2 is the new leading open weights model on Artificial Analysis

#46

Post by andai »

kingstnap wrote: post #13

According to many benchmarks this model is straight up frontier level and Zai seriously cooked. Some of these numbers are incredible. Excited to see if this turns out to be a Open Weight Opus 4.5 or better.

The only benchmarks that matters is your actual task.

I've had models that benched poorly but performed great. And I constantly see models at near the top of AA, which are terrible.

There doesn't necessarily seem to be a lot of overlap between benchmarks and real world usage. (Let alone common sense!)

As far as they go, though, these harder benchmarks match my experience more closely:

https://deepswe.datacurve.ai/

and https://cognition.ai/blog/frontier-code

Where we see "top" models drop way down in score when given longer tasks.

That being said, I've had a reasonably pleasant time with GLM-5.2 so far. (And have had an OK time with DeepSeek as well.)

By the time I'm done testing all the Chinese models, they'll be obsolete :)

Re: GLM-5.2 is the new leading open weights model on Artificial Analysis

#47

Post by epolanski »

vorticalbox wrote: post #29
Tiberium wrote: post #2

It seems to really be a nice step-up and is getting quite close to the frontier. I wish they'd start focusing on the reasoning efficiency now, though. I have a simple (relatively) test task to evaluate LLMs: writing a simple math evaluator library in Nim (it's about 400-600 lines total max), and GLM 5.2 (xhigh which maps to max effort) spent over 15 minutes (!) reasoning, spending about 45k tokens, before it finally…

This is a problem I find with opus is will spend so long thinking then going “but wait what if” To point where I stop it and simple tell it to “start writing code you can work it out as you go along” Seems writers block also effects LLM

Fable was 20 times worse on that.

It's clear it was the vibe coding model, as like no other model before, fully turned you into his assistant instead of the other way around.

Re: GLM-5.2 is the new leading open weights model on Artificial Analysis

#48

Post by epolanski »

andai wrote: post #23
Tiberium wrote: post #10

Earlier quoted context omitted.

Yes, but the Artificial Analysis result is also from GLM 5.2 (max), not high.

They have this with a lot of models, measuring only the max setting, while the one you'd actually want to use for most tasks is much lower.

For the brief period with had Fable, I never had to use it above medium.

Low nailed the overwhelming majority of mundane tasks on it's own, medium was good for more complex stuff.

Re: GLM-5.2 is the new leading open weights model on Artificial Analysis

#49

Post by mordae »

rahidz wrote: post #24

Correct me if I'm wrong, but neither DeepSeek nor GLM have image input modality. This makes them less useful when looking at UIs, photos, screenshots, etc. doesn't it? Or do they have alternate ways of doing so?

They do not and it sucks for certain tasks.

It also means that if they actually trained with vision, they'd be on par with Anthropic models as vision seems to improve model performance across the board even for non-vision tasks.

Re: GLM-5.2 is the new leading open weights model on Artificial Analysis

#50

Post by adrian_b »

rahidz wrote: post #24

Correct me if I'm wrong, but neither DeepSeek nor GLM have image input modality. This makes them less useful when looking at UIs, photos, screenshots, etc. doesn't it? Or do they have alternate ways of doing so?

That's right, but there are other recent open weights and relatively big LLMs that are multimodal, e.g. MiniMax-M3.

With open weights LLMs, it is affordable to use many different models, each for whatever it is better.

Moreover, for analyzing "UIs, photos, screenshots, etc." there are small models that can be run locally on smartphones or laptops, e.g. IBM granite-vision-4.1-4B, certain Google Gemma 4 variants and certain Qwen variants, whose output you can use as input for a big LLM, in order to accomplish some more complex task.

Post reply on HN